A knowledge-based interactive train scheduling system-aiming at large-scale complex planning expert systems

Abstract

By using AI multiple programming paradigms, a knowledge-based interactive train scheduling system is developed on the basis of EUREKA II. The approach is based on a goal-strategy-net hierarchical frame network that declaratively represents knowledge for scheduling. The field prototype system developed for subway train scheduling has been judged satisfactory by experts. The technology developed is considered not only useful for practical train scheduling system but also for building large-scale complex planning expert systems involving the allocation of the needed personnel.<>